{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2GGYX4G7YPTDELFXGHLE6NKKVA","short_pith_number":"pith:2GGYX4G7","schema_version":"1.0","canonical_sha256":"d18d8bf0dfc3e6322cb731d64f354aa81a9fc104dadb2e143813e33d34969ae7","source":{"kind":"arxiv","id":"2308.08833","version":2},"attestation_state":"computed","paper":{"title":"CMB: A Comprehensive Medical Benchmark in Chinese","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Dingjie Song, Feng Jiang, Guiming Hardy Chen, Haizhou Li, Jianquan Li, Qingying Xiao, Xiang Wan, Xidong Wang, Zhihong Chen, Zhiyi Zhang","submitted_at":"2023-08-17T07:51:23Z","abstract_excerpt":"Large Language Models (LLMs) provide a possibility to make a great breakthrough in medicine. The establishment of a standardized medical benchmark becomes a fundamental cornerstone to measure progression. However, medical environments in different regions have their local characteristics, e.g., the ubiquity and significance of traditional Chinese medicine within China. Therefore, merely translating English-based medical evaluation may result in \\textit{contextual incongruities} to a local region. To solve the issue, we propose a localized medical benchmark called CMB, a Comprehensive Medical B"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2308.08833","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-17T07:51:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"80d3f2578482033af6acbeb407d7ef35675983fe0f64ffe025efd6ddd85862a1","abstract_canon_sha256":"ae599be160e770a4ceae60b6a8b118061eb90007fb3497ad5854b8622e0d57fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:13.857112Z","signature_b64":"3r6nTfm15Bd2vgVt5M7hCWq/vPJQPd5JDHohoOj51Uu5uYDqbx6hM/gAyFDxyIMF4uQ1NkTK1vZ1eTBySy5KBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d18d8bf0dfc3e6322cb731d64f354aa81a9fc104dadb2e143813e33d34969ae7","last_reissued_at":"2026-07-05T08:04:13.856595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:13.856595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CMB: A Comprehensive Medical Benchmark in Chinese","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Dingjie Song, Feng Jiang, Guiming Hardy Chen, Haizhou Li, Jianquan Li, Qingying Xiao, Xiang Wan, Xidong Wang, Zhihong Chen, Zhiyi Zhang","submitted_at":"2023-08-17T07:51:23Z","abstract_excerpt":"Large Language Models (LLMs) provide a possibility to make a great breakthrough in medicine. The establishment of a standardized medical benchmark becomes a fundamental cornerstone to measure progression. However, medical environments in different regions have their local characteristics, e.g., the ubiquity and significance of traditional Chinese medicine within China. Therefore, merely translating English-based medical evaluation may result in \\textit{contextual incongruities} to a local region. To solve the issue, we propose a localized medical benchmark called CMB, a Comprehensive Medical B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.08833","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2308.08833/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2308.08833","created_at":"2026-07-05T08:04:13.856667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.08833v2","created_at":"2026-07-05T08:04:13.856667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.08833","created_at":"2026-07-05T08:04:13.856667+00:00"},{"alias_kind":"pith_short_12","alias_value":"2GGYX4G7YPTD","created_at":"2026-07-05T08:04:13.856667+00:00"},{"alias_kind":"pith_short_16","alias_value":"2GGYX4G7YPTDELFX","created_at":"2026-07-05T08:04:13.856667+00:00"},{"alias_kind":"pith_short_8","alias_value":"2GGYX4G7","created_at":"2026-07-05T08:04:13.856667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31432","citing_title":"Clinically Structured Rank-Gated LoRA for Cross-Benchmark Medical Question Answering","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31432","citing_title":"Clinically Structured Rank-Gated LoRA for Cross-Benchmark Medical Question Answering","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29375","citing_title":"TriageRA-CCF: Source-Side Clinical Confidence and Coverage Signals for Adaptive Rank Budgeting in Medical LLMs","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":128,"is_internal_anchor":false},{"citing_arxiv_id":"2503.17599","citing_title":"Evaluating Clinical Competencies of Large Language Models with a General Practice Benchmark","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13116","citing_title":"A Survey on Knowledge Distillation of Large Language Models","ref_index":242,"is_internal_anchor":false},{"citing_arxiv_id":"2412.18925","citing_title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12138","citing_title":"Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinions","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2GGYX4G7YPTDELFXGHLE6NKKVA","json":"https://pith.science/pith/2GGYX4G7YPTDELFXGHLE6NKKVA.json","graph_json":"https://pith.science/api/pith-number/2GGYX4G7YPTDELFXGHLE6NKKVA/graph.json","events_json":"https://pith.science/api/pith-number/2GGYX4G7YPTDELFXGHLE6NKKVA/events.json","paper":"https://pith.science/paper/2GGYX4G7"},"agent_actions":{"view_html":"https://pith.science/pith/2GGYX4G7YPTDELFXGHLE6NKKVA","download_json":"https://pith.science/pith/2GGYX4G7YPTDELFXGHLE6NKKVA.json","view_paper":"https://pith.science/paper/2GGYX4G7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.08833&json=true","fetch_graph":"https://pith.science/api/pith-number/2GGYX4G7YPTDELFXGHLE6NKKVA/graph.json","fetch_events":"https://pith.science/api/pith-number/2GGYX4G7YPTDELFXGHLE6NKKVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2GGYX4G7YPTDELFXGHLE6NKKVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2GGYX4G7YPTDELFXGHLE6NKKVA/action/storage_attestation","attest_author":"https://pith.science/pith/2GGYX4G7YPTDELFXGHLE6NKKVA/action/author_attestation","sign_citation":"https://pith.science/pith/2GGYX4G7YPTDELFXGHLE6NKKVA/action/citation_signature","submit_replication":"https://pith.science/pith/2GGYX4G7YPTDELFXGHLE6NKKVA/action/replication_record"}},"created_at":"2026-07-05T08:04:13.856667+00:00","updated_at":"2026-07-05T08:04:13.856667+00:00"}